© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 118618
    Prev
    Next
    INDEX
    Explanations

    references to countries, particularly Australia and Britain

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĢ£
    -0.07
    uke
    -0.07
    ìĦľ
    -0.06
    IEL
    -0.06
    mong
    -0.06
     Pear
    -0.06
    ANGO
    -0.06
    +":
    -0.06
    baÅŁ
    -0.06
    uru
    -0.06
    POSITIVE LOGITS
    's
    0.08
     Ferr
    0.06
    ’s
    0.06
     Beckham
    0.06
    thouse
    0.06
    tras
    0.05
     nationwide
    0.05
     gutter
    0.05
     leak
    0.05
     Bain
    0.05
    Activations Density 0.038%

    No Known Activations